paper-with-me

홈 › Papers

Incorporating Music Knowledge in Continual Dataset Augmentation for Music Generation

2020-06-23 · Alisa Liu, Alexander Fang, Gaëtan Hadjeres, Prem Seetharaman, Bryan Pardo

Deep learning has rapidly become the state-of-the-art approach for music generation. However, training a deep model typically requires a large training set, which is often not available for specific musical styles. In this paper, we present augmentative generation (Aug-Gen), a method of dataset augmentation for any music generation system trained on a resource-constrained domain. The key intuition of this method is that the training data for a generative system can be augmented by examples the system produces during the course of training, provided these examples are of sufficiently high quality and variety. We apply Aug-Gen to Transformer-based chorale generation in the style of J.S. Bach, and show that this allows for longer training and results in better generative output.

📄 PDF Abstract BibTeX arXiv:2006.13331

Code (1)

asdfang/constraint-transformer-bach 공식 구현 pytorch

Tasks

Music Generation

Similar Papers 제목 키워드 기반

AVQACL: A Novel Benchmark for Audio-Visual Question Answering Continual Learning

2025-01-01 · CVPR 2025 1 · Kaixuan Wu, Xinde Li, Xinling Li, Chuanfei Hu 외

In this paper, a novel benchmark for audio-visual question answering continual learning (AVQACL) is introduced, aiming to study fine-grained scene understanding and spatial-temporal reasoning in videos under a contin…

Audio-visual Question AnsweringContinual LearningKnowledge DistillationQuestion Answering+2

Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation

2026-05-18 · Yizhu Wen, Shuhao Zhang, Nan Zhang, Long Cheng 외 arxiv

Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption dataset. This design introduces an integrity dependency on the music knowledge database. W…

Text-to-Music Generation

Data Augmentation for Continual RL via Adversarial Gradient Episodic Memory

2024-08-24 · Sihao Wu, Xingyu Zhao, Xiaowei Huang

Data efficiency of learning, which plays a key role in the Reinforcement Learning (RL) training process, becomes even more important in continual RL with sequential environments. In continual RL, the learner interacts wi…

BenchmarkingData AugmentationReinforcement Learning (RL)

Knowledge-guided Continual Learning for Behavioral Analytics Systems

2025-10-25 · Yasas Senarath, Hemant Purohit arxiv

User behavior on online platforms is evolving, reflecting real-world changes in how people post, whether it's helpful messages or hate speech. Models that learn to capture this content can experience a decrease in perfor…

Continual LearningData Augmentation

Music's Multimodal Complexity in AVQA: Why We Need More than General Multimodal LLMs

2025-05-27 · Wenhao You, Xingjian Diao, Chunhui Zhang, Keyi Kong 외

While recent Multimodal Large Language Models exhibit impressive capabilities for general multimodal tasks, specialized domains like music necessitate tailored approaches. Music Audio-Visual Question Answering (Music AVQ…

Audio-visual Question AnsweringQuestion AnsweringVisual Question Answering